教学课程资源库 更多>>

关键词： Authentication   Security   Servers   Privacy   Edge computing   Blockchains   Computer science   5G mobile communication   Vehicle dynamics   Advanced driver assistance systems   Blockchain   revocation   fog server   pseudonym authentication   fifth generation(5g)   vehicular fog computing  

摘要： The driving experience in fifth-generation (5G)-assisted vehicular fog computing systems has improved thanks to recent advancements in intelligent transportation. However, in the present vehicular system setup, the phenomenon of providing low computation overhead with massive serving capability is crucial. In the existing scenario, the computational complexity rises when an authenticated driver travels from one roadside unit (RSU) area to another RSU region and must undergo re-authentication by the existing RSU. In this paper, an efficient blockchain-based pseudonym authentication scheme to address these issues and avoiding using RSU for 5G-assisted vehicular fog computing. The pseudonym identity generated for each vehicles and fog servers in order to exchange information about the road environment. The proposed scheme avoids re-authentication by the future fog server by utilising bilinear pairing of points on the elliptic curve and utilising blockchain technology without the need for a trusted authority. For fog computing, fog server obtains the verification key to authenticate the messages sent from vehicles for supporting revocation. The security analysis part of this work shows that the proposed scheme is not only satisfy requirements of security and privacy, but also resistance security attacks. Finally, the evaluation of the proposed scheme's performance shows that it is more efficient than existing schemes with regards to computation cost, verification speed, and energy consumption.

关键词： Computer Science   Economics, Finance, Business & Industry   Engineering & Technology   MathML  

ISBN: (数字)9788770040167 ISBN: (纸本)9788770040174

摘要： This book emphasizes the applications of advances in data processing methods for Artificial Intelligence in today"s fast-changing world, as well as to serve society through research, innovation, and development in this field. This book is applicable to a wide range of data that contribute to data science concerns and can be used to promote research in this high-potential new field. People"s perceptions of the world and how they conduct their lives have changed dramatically as a result of technological advancements. The world has been gripped by technology, and the advances that are being made every day are undeniably transforming the planet. In the domains of Big Data, engineering, and data science, this cutting-edge technology is ready to support us. Artificial intelligence (AI) is a current research topic because it can be applied to a wide range of applications and disciplines to solve complicated problems and find optimal solutions. In research, medicine, technology, and the social sciences, the benefits of AI have already been proven. Data science, also known as pattern analytics and mining, is a technique for extracting useful and relevant information from databases, enabling better decision-making and strategy formulation in a range of fields. As a result of the exponential growth of data in recent years, the combined notions of big data and AI have given rise to many study areas, such as scale-up behaviour from classical algorithms. Furthermore, combining numerous AI technologies from other areas (such as vision, security, control, and biology) in order to build efficient and durable systems that interact in the real world is a new problem. Despite recent improvements in fundamental AI technologies, the integration of these skills into larger, trustworthy, transparent, and maintainable systems is still in its development. Both conceptually and practically, there are a number of unanswered issues.

关键词： Dentistry   Teeth   Diseases   Accuracy   Diagnostic radiography   Computational modeling   Solid modeling   Training   Convolutional neural networks   Computer science   Deep learning   periodontal disease   tooth decay   dental radiographs  

摘要： Dental health plays a pivotal role in determining the general health and quality of life of a person. Dental caries is a prevalent health problem in the world;therefore, prompt and effective dental caries treatment is necessary for individuals who require pain relief. Conventional methods of diagnosing dental diseases, like visual examination and radiographic testing, depend on qualified medical professionals and can be incredibly labor-intensive and imprecise in their diagnosis. To overcome these challenges, this study designed a deep learning (DL) model for the diagnosis of several dental conditions such as tooth decay, non-periodontal, and periodontal disease. A novel model named periodontal disease classification network (PDCNET) based on convolutional neural network (CNN) has been developed for the identification of periodontal disease using dental radiographs. Additionally, the proposed PDCNET model has been evaluated on two publicly available benchmark datasets of dental caries. To handle the imbalanced classes of the dental caries dataset, this study used the SMOTE TOMEK method to generate new synthetic samples for the minority categories to ensure the periodontal disease dataset is balanced. The proposed PDCNET model acquired a 99.79% AUC, 98.39% recall, 98.39% accuracy, 98.39% precision, and an F1-score of 98.31%. Furthermore, the performance of the proposed PDCNET model is contrasted using the six baseline pre-trained classifiers such as EfficientNet-B0 (M1), DenseNet-201 (M2), Vgg-16 (M3), Vgg-19 (M4), Inception-V3 (M5), and MobileNet (M6) in terms of many parameters. The levels of accuracy attained by M1, M2, M3, M4, M5, and M6 are 85.94%, 94.37%, 91.96%, 93.57%, 89.95%, and 94.77%, respectively. The findings showed that the PDCNET model has superior outcomes as compared to baseline models and provides significant assistance to the dentist in the diagnosis of dental disease.

关键词： Image fusion   Semantics   Visualization   Training   Data mining   Computer science   Object detection   Deep learning   high-level vision task   image fusion   infrared image   mask   self-attention   visible image  

摘要： In the field of image fusion, the fusion of infrared and visible images emerges as a crucial work, retaining the inherent characteristics of each source image for the creation of high-quality fusion images. However, existing fusion algorithms primarily prioritize the visual performance and statistical metrics, often neglecting the requisites of high-level vision tasks. To bridge this gap, this article proposes SIGFusion, an end-to-end method for infrared and visible image fusion. SIGFusion not only considers the visual performance and statistical metrics of the fused image but also focuses on meeting the demands of subsequent high-level vision tasks, thereby enhancing performance in fusion and high-level vision tasks. Concretely, we define significant semantic information as salient targets presenting in both infrared and visible images. By utilizing targets, our fusion network is guided to enhance these salient targets. In contrast to the isolated employ of either infrared or visible images, our target-based method comprehensively utilizes the semantic information within the image. In addition, the utilization of target-based self-attention loss enhances the extraction of vital information from the source image. It is worth noting that masks are only necessary during the training stage and are automatically generated through detection algorithms. We conduct experiments in both image fusion and high-level vision tasks. Experimental results demonstrate the effectiveness of SIGFusion in both infrared and visible image fusion tasks, as well as in subsequent high-level vision tasks. The source code is available at: https://***/poison-pig/SIGFusion.

ISBN: (纸本)9783031500770

关键词： Design automation   Solid modeling   Industries   Three-dimensional printing   Product development   Collaboration   Optimization methods   Computer science   art   digital visualizations   interactive installations   innovation  

摘要： The intersection of computer science and art has sparked a wave of innovation, particularly in digital visualizations and interactive installations. This abstract explores the symbiotic relationship between these disciplines, highlighting groundbreaking advancements and creative endeavors. Innovations in digital visualizations leverage algorithms and computational techniques to transform data into visually engaging representations. From intricate data sculptures to immersive virtual reality experiences, computer scientists and artists collaborate to push the boundaries of storytelling and communication. These visualizations not only convey complex information effectively but also evoke emotional responses, bridging the gap between technology and human perception. Interactive installations blur the lines between audience and artwork, inviting participation and engagement. Through sensors, augmented reality, and responsive environments, users become active participants in the creation of art, shaping and influencing their experiences in real-time. This dynamic interaction fosters new forms of expression and challenges traditional notions of artistic production. By exploring the intersection of computer science and art, this abstract underscores the transformative power of interdisciplinary collaboration. Through experimentation, exploration, and innovation, digital visualizations and interactive installations continue to redefine the possibilities of creative expression in the digital age.

关键词： Time series analysis   Predictive models   Forecasting   Recurrent neural networks   Deep learning   Convolutional neural networks   Data models   Learning analytics   hybrid objective functions   deep time series neural network   LSTM model optimization  

摘要： In the realm of education, the timely identification of potential challenges, such as learning difficulties leading to dropout risks, and the facilitation of personalized learning, emphasizes the crucial importance of early grade prediction. This study seeks to connect predictive modeling with educational outcomes, particularly focusing on addressing these challenges in computer science higher education programs. To address these issues, nonlinear dynamic systems, notably Recurrent Neural Networks (RNNs), have demonstrated efficacy in unraveling the intricate relationships within student learning traces, surpassing the constraints of traditional time series methods. However, the challenge of vanishing gradient issues hampers RNNs, leading to a significant decrease in gradient values during weight matrix multiplication. To solve this challenge, we introduce an innovative loss function, the MSECosine loss function crafted by seamlessly combining two established loss functions: Mean Square Error (MSE) and LogCosh. In assessing the performance of this novel loss function, we employed two self-collected datasets comprising learning management system (LMS) and assessment records from a higher education computer science program. These datasets serve as the testing ground for four deep time series models: Multilayer Perceptron (MLP), Convolutional Neural Network (CNN), Long Short-Term Memory network (LSTM), and CNN-LSTM. Employing 29 meticulously designed feature sets representing combination of demography, learning activities and assessment, LSTM emerges as the preeminent model which is consistent with our expectation that RNN is the best suited approach. Building on this groundwork, we solve the vanishing gradient issue and boost the LSTM model's performance by integrating the proposed MSECosine loss function, resulting in an enhanced model termed eLSTM. Experimental results underscore the noteworthy achievements of the eLSTM model, emphasizing an accuracy of 0.6191% and

关键词： Tensors   Clustering algorithms   Clustering methods   Correlation   Computer science   Symbols   Sun   Graph embedding   incomplete multi-view   multi-view clustering   one-step   tensor low-rank constraint  

摘要： Traditional multi-view algorithms typically require data to be complete, and these algorithms may not be suitable or effective when dealing with incomplete data. As a result, the research field has witnessed the emergence of methods specifically designed for addressing incomplete multi-view clustering. In contrast, most of existing incomplete multi-view algorithms primarily emphasize capturing global information while neglecting the importance of local information. To overcome these challenges, we put forward a novel approach, named tensor low-rank graph embedding and learning for one-step incomplete multi-view clustering. We combine the beneficial aspects of graph embedding and tensor low-rank in this method, which not only focuses on local relationships but also provides insights into the global structure. Firstly, the initial similarity graph matrix is constructed using the inter-dependency between views. Secondly, the similarity graph matrix is structured as a third-order tensor and constrained by the tensor nuclear norm. This constraint enables the capturing of higher-order correlations across multiple views. Thirdly, graph embedding is added to obtain a common feature representation. Finally, the algorithm incorporates clustering to determine the optimal clustering labels. We conducted experiments comparing our algorithm with seven different incomplete multi-view methods using four different evaluation metrics. The experimental results indicate that our algorithm achieved the best clustering performance across five datasets under various missing rates. Especially when faced with a 50% missing rate in the Extended YaleB dataset, the clustering accuracy and normalized mutual information of our method are improved by 28.23% and 28.11%, respectively, compared to the second-best algorithm.

关键词： Quantum computing   Boolean functions   Qubit   Computational modeling   Quantum entanglement   Machine learning   Costs   Testing   Computer science   Time complexity   Quantum algorithm   junta problem   Mz   entanglement  

摘要： Detecting junta variables is a critical issue in Boolean function analysis, circuit design optimization, and machine learning feature selection. In this paper, we investigate a novel quantum computation algorithm based on the Mz operator. The algorithm takes in an unknown oracle concealing a Boolean function with n variables and an unknown input state, which can be quantum or classical. The input state can be complete or incomplete quantum basis states, and it can be a weighted or uniform superposition of basis states. The proposed approach determines whether a given variable is a junta with a time cost of O (2 /& varepsilon;(2) ) and a memory cost of 2n+ 6. The algorithm is analyzed and experimentally implemented using the Qiskit simulator and IBM's real quantum computer. Experimental results show that the proposed approach achieved a quantum supremacy ratio 6300% higher than that of the classical method when verifying junta variables for Boolean functions with 12 variables. The results suggest that the proposed quantum method can verify junta variables in scenarios beyond the capabilities of current classical or quantum methods.